#Trabajando con bupa
bupa<-read.csv("https://raw.githubusercontent.com/VictorGuevaraP/Mineria-de-datos-2019-2/master/bupa.txt", sep = ",")
library(Amelia)
## Loading required package: Rcpp
## ## 
## ## Amelia II: Multiple Imputation
## ## (Version 1.7.5, built: 2018-05-07)
## ## Copyright (C) 2005-2019 James Honaker, Gary King and Matthew Blackwell
## ## Refer to http://gking.harvard.edu/amelia/ for more information
## ##
missing(bupa)
## [1] FALSE

Como primer paso decidí utilizar el paquete “Amelia” para poder identificar si existe missings en la data.

##PRUEBA DE CORRELACIONES INDIVIDUALES
cor(bupa)
##             V1          V2          V3        V4        V5          V6
## V1  1.00000000  0.04410300  0.14769505 0.1877652 0.2223145  0.31267960
## V2  0.04410300  1.00000000  0.07620761 0.1460565 0.1331404  0.10079606
## V3  0.14769505  0.07620761  1.00000000 0.7396749 0.5034353  0.20684793
## V4  0.18776515  0.14605655  0.73967487 1.0000000 0.5276259  0.27958777
## V5  0.22231449  0.13314040  0.50343525 0.5276259 1.0000000  0.34122396
## V6  0.31267960  0.10079606  0.20684793 0.2795878 0.3412240  1.00000000
## V7 -0.09107012 -0.09805018 -0.03500879 0.1573558 0.1463925 -0.02204853
##             V7
## V1 -0.09107012
## V2 -0.09805018
## V3 -0.03500879
## V4  0.15735580
## V5  0.14639252
## V6 -0.02204853
## V7  1.00000000
library(corrplot)
## corrplot 0.84 loaded
corrplot(cor(bupa))

Azul es correlacion positiva ambos aumentan Rojo es correlacion negativa una aumenta y otra disminuye

#Uso de la libreria PerformanceAnalytics
library(PerformanceAnalytics)
## Loading required package: xts
## Loading required package: zoo
## 
## Attaching package: 'zoo'
## The following objects are masked from 'package:base':
## 
##     as.Date, as.Date.numeric
## Registered S3 method overwritten by 'xts':
##   method     from
##   as.zoo.xts zoo
## 
## Attaching package: 'PerformanceAnalytics'
## The following object is masked from 'package:graphics':
## 
##     legend
chart.Correlation(bupa)

Con esta libreria se busca visualizar la correlacion entre las variables

#Uso de libreria psych
library(psych)
cortest(cor(bupa))
## Warning in cortest(cor(bupa)): n not specified, 100 used
## Tests of correlation matrices 
## Call:cortest(R1 = cor(bupa))
##  Chi Square value 208.01  with df =  21   with probability < 9.6e-33

Se rechaza H0, por lo cual hay evidencia para saber que las correlaciones son distintas

##PRUEBA DE ESFERICIDAD DE BARLETT
library(rela)
cortest.bartlett(cor(bupa), n=345)
## $chisq
## [1] 544.8724
## 
## $p.value
## [1] 6.004754e-102
## 
## $df
## [1] 21

Determinante de la matriz Pvalue es 6.004 se rechaza Hp , lo cual significa que no existe correlacion entre las variables

##PRUEBA KMO
KMO(bupa)
## Kaiser-Meyer-Olkin factor adequacy
## Call: KMO(r = bupa)
## Overall MSA =  0.64
## MSA for each item = 
##   V1   V2   V3   V4   V5   V6   V7 
## 0.70 0.53 0.59 0.63 0.81 0.73 0.23

Según el resultado se justifica la realizacion del PCA (ya que MSA>0.5)

#Grafico de sedimentación
scree(bupa)

Segun el gréfico de sedimentacion deberia tomarse tres componentes

#Analisis paralelo
fa.parallel(bupa, fa="pc")

## Parallel analysis suggests that the number of factors =  NA  and the number of components =  2

Usamos la funcion “fa.parallel” del paquete “psych”, dicha funcion nos ayudará a realziar gráficos de pantalla de datos o matrices de correlación en comparación con matrices aleatorias

#Asignamos una variable llamada componentes
componentes<-prcomp(bupa, scale=TRUE,center = TRUE)
componentes
## Standard deviations (1, .., p=7):
## [1] 1.5837765 1.0926330 1.0046350 0.9465752 0.8188865 0.7061828 0.4724823
## 
## Rotation (n x k) = (7 x 7):
##           PC1        PC2         PC3         PC4         PC5         PC6
## V1 0.26093155  0.4869910  0.49039467 -0.02430417  0.67017404  0.04830950
## V2 0.14769977  0.3252950 -0.66587263 -0.62523056  0.15949171  0.06888411
## V3 0.50668951 -0.1526510 -0.23040936  0.41245134  0.03558136  0.19739104
## V4 0.53762897 -0.2217274 -0.14693268  0.13167289  0.08655906  0.36430265
## V5 0.49239652 -0.1143955  0.03814116 -0.10572417 -0.07449247 -0.84970661
## V6 0.34359042  0.3470071  0.37146594 -0.27134023 -0.69137189  0.25772936
## V7 0.06173834 -0.6716080  0.31938586 -0.57986125  0.18200666  0.18115126
##            PC7
## V1  0.04700907
## V2  0.08880155
## V3  0.67566973
## V4 -0.69473462
## V5 -0.06539520
## V6  0.07416000
## V7  0.20234232

Usamos la función “prcomp” la cual realiza un analisis de componentes principales en la matriz de datos dada y devuelve los resultados como un objeto

#Se realiza un resumen de la varaible componentes
summary(componentes)
## Importance of components:
##                           PC1    PC2    PC3    PC4    PC5     PC6     PC7
## Standard deviation     1.5838 1.0926 1.0046 0.9466 0.8189 0.70618 0.47248
## Proportion of Variance 0.3583 0.1706 0.1442 0.1280 0.0958 0.07124 0.03189
## Cumulative Proportion  0.3583 0.5289 0.6731 0.8011 0.8969 0.96811 1.00000

En este caso usaremos 4 variables para hacer el analisis, a pesar de que los graficos realizados anteriormente no cumplen con esta condición (nos basamos en la varianza de la data)

La Desviacion estandar = que tan lejos o cerca esta de la media

#Grafico de los componentes
plot(componentes)

Se realizó un gráfico para poder visualizar la data que contiene la variable componentes

#Grafico de componentes con aplicacion de escalado
biplot(componentes, scale=1)

Se usa la funcioón “biplot” para realizar un gráfico de la data, junto a ello se puede ver que la data se escaló a 1

#Extraemos los componentes
componentes_prin<-componentes$x
componentes_prin<-componentes_prin[,1:4]
head(componentes_prin)
##             PC1         PC2        PC3        PC4
## [1,] -0.1390785  0.11105334 -2.3448572  0.5938918
## [2,]  0.2907050 -1.94038272 -0.9286607  0.7578934
## [3,] -0.8721346 -1.54263788  0.1152322  0.2507909
## [4,] -0.1580974 -0.70132800 -0.3506241 -0.4200923
## [5,] -1.1408941 -1.12133672 -0.3251554 -0.4683007
## [6,] -1.0901984  0.03114855  1.5875375 -0.1588787

Se asigna una nueva variable donde se asignan los datos de “componentes”, y en el cual solo se trabaja con 4 datos

#Exportamos los componentes 
write.csv(componentes_prin, file = "componentes_clientes.csv")
getwd()
## [1] "C:/Users/HP-PC/Desktop"
#Visualizamos los componentes
componentes_prin
##                 PC1           PC2          PC3          PC4
##   [1,] -0.139078519  0.1110533377 -2.344857197  0.593891769
##   [2,]  0.290705050 -1.9403827160 -0.928660655  0.757893404
##   [3,] -0.872134616 -1.5426378773  0.115232185  0.250790947
##   [4,] -0.158097379 -0.7013279958 -0.350624109 -0.420092305
##   [5,] -1.140894140 -1.1213367230 -0.325155359 -0.468300724
##   [6,] -1.090198437  0.0311485470  1.587537520 -0.158878701
##   [7,] -1.612463399  0.4396000189 -0.449884031  0.959132000
##   [8,] -1.841668406  0.6467797535 -0.553614217  0.726001765
##   [9,] -1.255115033  0.6597858732  0.212086981  1.296802232
##  [10,] -1.324740147  0.5515859229 -0.248930519  1.158986808
##  [11,] -1.366885730  0.2548515157  0.009578532  1.221890992
##  [12,] -1.967072925 -0.2113132673 -1.070118320  0.912341920
##  [13,]  0.437085004  0.0311524476 -1.001216480  1.932179260
##  [14,] -1.259467244  0.3771708306 -1.294255204  0.566523580
##  [15,] -0.683870253  1.2617814162  0.102512256  0.969140440
##  [16,] -0.446928018  0.7170640844 -0.895453335  0.556431904
##  [17,] -1.476523381  0.6333770379 -0.540950015  0.830921686
##  [18,] -1.407048489  0.8535550954 -0.914372183  0.292094756
##  [19,] -0.324419551  1.3628174597 -1.750407350 -0.678053516
##  [20,] -0.179719706  1.7659819007 -1.873526520 -0.900102933
##  [21,] -1.100689599  0.7659745550 -0.009028676  1.277312251
##  [22,] -0.945357877  0.0800668644  1.306507384  2.587501512
##  [23,] -0.949328465  0.3909872924 -0.342106598  1.221374091
##  [24,] -0.914533852  1.3642845144  0.218485026  0.667916264
##  [25,]  0.957455616 -0.4993700176 -2.011040940  0.910647790
##  [26,] -1.209977916  1.0266561615 -0.271546096  0.651095914
##  [27,] -1.402093775  0.3478706464  0.258467228  1.578055253
##  [28,] -1.354045990  0.4194811856 -0.652476623  0.872463010
##  [29,] -1.280616945  1.5596796206 -1.467279100 -0.563011913
##  [30,] -1.359889055 -0.1927195764  0.049709273  1.920040380
##  [31,] -1.338262878  0.4581660425 -1.359438623  0.525228486
##  [32,] -0.456633883  0.3649928216 -0.123102888  1.335261234
##  [33,] -0.582501748  1.0787632644 -0.579889431  0.633532853
##  [34,] -0.528493053  0.8013538274 -1.806553190 -0.061536806
##  [35,] -1.105903737  1.1061809216  0.066456804  0.874090134
##  [36,]  5.914578444 -2.8057471295 -2.103711197  2.753178193
##  [37,] -0.009063968 -1.9909335002 -0.383966289  0.820135743
##  [38,] -2.249641776 -2.3092909123  0.080357432  0.518369767
##  [39,] -0.604380724 -1.1383050547 -1.139264647 -0.814409090
##  [40,] -0.792965043 -0.9737282135  0.207327180 -0.207756308
##  [41,]  1.273132184 -1.7432200992 -2.158305506 -0.032342725
##  [42,]  0.364344497 -1.3309666243 -0.271245964 -0.098062312
##  [43,] -0.689368602 -0.2903659093 -1.198202671 -1.496757266
##  [44,] -1.552174985 -0.6866217469 -0.748479141 -1.053051108
##  [45,] -1.556926331 -1.1935568084 -0.249896030 -0.257547794
##  [46,] -1.257738083 -1.0287295058  0.189814916 -0.159413494
##  [47,] -1.497904062 -0.5214324921  0.941390239 -0.173909833
##  [48,]  0.001806900 -0.7315537670  1.220233788  0.341243957
##  [49,] -0.810883595 -0.5073863543 -0.063112076 -0.528721519
##  [50,] -0.933154413 -2.1876746082  0.248514947  0.779899234
##  [51,] -0.949958211 -0.7415669159 -0.198015458 -0.589790373
##  [52,] -1.251402633 -1.3593089102 -0.325390021 -0.121092618
##  [53,]  1.880390648 -1.5686172965  0.100426283  0.895108550
##  [54,] -0.735015339 -0.6712154283  1.417517635  0.027064665
##  [55,] -1.230509177 -1.3189045732  0.428293389  0.123066200
##  [56,] -0.845216955 -1.4996274685 -0.448180803 -0.095500246
##  [57,] -1.196135197 -1.1274738981 -1.031095813 -0.827055004
##  [58,] -1.199690731 -1.2888225996  0.604740532  0.267569709
##  [59,] -0.002776649 -0.2784313214  0.720742189 -0.256151228
##  [60,] -0.696241339 -0.9115691462  0.245576062 -0.123182511
##  [61,] -0.035618378 -1.5301590986  0.649479137  0.803191863
##  [62,] -1.439495084 -0.4580094372  0.162594879 -0.742840573
##  [63,] -2.214008457 -0.4029091553  1.105225878 -0.458492301
##  [64,] -1.229744055 -0.8447549507  0.877878341  0.064803653
##  [65,] -0.902970392  0.3512667848 -0.984524742  0.848600931
##  [66,] -0.940084255  0.7248325702 -0.933301689  0.541013219
##  [67,] -1.663984764 -0.5661537790  0.362642052 -0.760941653
##  [68,] -0.995288265 -1.6324897626  0.160894564  0.317382447
##  [69,]  0.267118242  0.7154336111  1.259703751 -0.641348382
##  [70,] -1.138205512 -0.7017678631  0.429769078 -0.345248522
##  [71,] -0.176368287  0.4897631380 -0.245977214  0.931650341
##  [72,] -0.477995973  0.6659760813 -0.424974976  0.929091832
##  [73,] -1.035651719  0.3920610828 -0.694020256  0.919730803
##  [74,] -0.511894128  0.7739995592 -0.672747710  0.764671434
##  [75,] -1.338300363  0.1262186276 -0.264705712  1.154214776
##  [76,] -0.968114516  1.1113865523 -0.628038665  0.063617221
##  [77,]  1.862355665 -1.2268181164 -1.052617329 -1.050364505
##  [78,] -0.205374472  0.1222118790  0.778963840 -0.581618443
##  [79,] -0.984019411 -0.6693469042  0.967848027 -0.260411047
##  [80,]  0.078807063 -0.0052547813  0.375177687 -0.723256046
##  [81,]  0.963324256 -0.1899244037 -0.912900548 -1.368822774
##  [82,] -0.061434548 -1.2367391996  0.589539862  0.437806344
##  [83,]  0.654463738 -0.3236637103 -1.135467987 -0.957574303
##  [84,] -0.720764882 -0.2565164757  1.159926065 -0.243890627
##  [85,]  3.291818635 -1.4984552408  0.892491094 -0.723010440
##  [86,] -0.720764882 -0.2565164757  1.159926065 -0.243890627
##  [87,] -0.384693658 -1.3873066626  0.642069190  0.513977789
##  [88,] -0.724921574 -0.4247561022  0.613908073 -0.418686252
##  [89,] -0.746343747  1.3512708588 -0.413101394  0.230877451
##  [90,] -1.018452853  0.4634748466 -1.493520227  0.172193420
##  [91,] -0.698128280  0.6134542163 -0.513949539  0.705952014
##  [92,] -1.462517570  0.1749759450  0.069218193  1.291233533
##  [93,]  1.060392399  1.4406831748  0.293233860  1.125394733
##  [94,] -1.436844820  0.8396205156 -0.273427976  0.601433664
##  [95,]  0.107251558  0.3184197343 -0.500297642  1.355925167
##  [96,] -1.022657034  0.6475204916  0.430111687  1.134753363
##  [97,]  0.282997729 -2.1059675920 -0.651928695  0.051992451
##  [98,]  0.368758711 -0.3933089877 -0.352905134 -1.522045905
##  [99,] -0.599508389 -0.6441218350  0.416605117 -0.457643900
## [100,] -0.066200474 -0.2796527802  0.255977819 -0.677821304
## [101,] -0.939565511 -1.1926127659  0.165286095 -0.196673044
## [102,] -0.366093139 -0.3449895941  1.103703985 -0.693445198
## [103,] -0.586805740  0.6918111712 -0.155050899  0.805480087
## [104,] -0.639006455  1.2842869519 -0.698388506 -0.060560990
## [105,] -0.687134714  1.2907906228 -1.341387128 -0.331537180
## [106,] -0.487726499  0.0918080044  0.779684703  1.872634327
## [107,]  0.056451985  1.1334102859 -0.653729428  0.434198456
## [108,] -0.354207123  1.8813319646 -1.550913980 -0.719005501
## [109,] -1.796056624  1.4787698222  0.370169286  0.340964282
## [110,]  0.143221704 -0.0133341783 -1.157635855 -1.912825615
## [111,]  1.008588103 -1.2692595625 -0.610980906 -0.430618852
## [112,] -0.313969527 -0.4688937350 -0.565919590 -1.095531879
## [113,] -0.770281995 -1.2216882233  1.050656239  0.372346087
## [114,] -0.350817075 -0.4668989900 -0.223770823 -0.944147845
## [115,]  3.343660823 -1.0141870992 -0.904719787 -1.384315646
## [116,] -1.557447275 -0.5681110714  0.318283764 -0.871604659
## [117,] -0.784929399 -0.6005337292  1.804823993  0.215192049
## [118,] -1.120880710 -0.9983095616  0.309463819 -0.438437089
## [119,] -0.772362067  0.0432205719 -0.245600362 -1.606831871
## [120,] -1.087002418 -0.2746284321  1.178384639 -0.482067441
## [121,]  1.601896039 -0.6033159039  1.102014989  0.487202113
## [122,] -0.709393619 -1.0867099232 -1.918845188 -1.748545850
## [123,] -0.363190994  0.9065889253 -1.774874598 -3.063939682
## [124,] -0.709900668 -0.2823775158  0.214927182 -1.095869224
## [125,]  0.166120071 -0.3603921039 -0.770203489 -1.292996955
## [126,] -1.195001692 -0.1676998912  0.764259030 -0.923061895
## [127,]  0.002658052 -0.1552907293  0.559782809 -0.863289511
## [128,]  0.703379466 -0.8684950863  0.986397739 -0.159882036
## [129,] -1.319562644 -1.4959504916  0.608758081  0.128612668
## [130,] -0.936516936 -0.0874270888  0.438967756 -1.013683263
## [131,] -0.608798986  1.3605445740  0.372853665  0.378569674
## [132,] -0.525767443  1.3773740759  0.489162915  0.647591488
## [133,]  2.092741541 -1.3680050242 -0.648927788 -0.519419941
## [134,]  5.038069982 -1.5403278379  0.972559253  1.936883455
## [135,] -1.092529311 -0.6275749731  0.728413461 -0.559635684
## [136,] -1.505851514 -0.8824376578  1.211401742 -0.028934316
## [137,] -0.822369055 -0.6037517609  0.532205836 -0.728118460
## [138,] -0.320406172 -0.2798233434  1.232707892 -0.366574992
## [139,]  0.899721807 -0.5618764273  0.580629676 -0.956490279
## [140,] -0.349200753  0.6734887544  2.026803668 -0.580233774
## [141,] -0.307688399  1.6163536563 -0.052673936 -0.246474473
## [142,]  0.009453415  1.5298487893  0.881144567  0.683000543
## [143,] -0.176403759  1.1026904032  0.272056552  0.668832279
## [144,]  0.182144751  1.1495193890  0.370295683  0.829127551
## [145,] -0.999041682  1.6683866795  1.501735000  0.679324314
## [146,]  0.246297190  1.1820289562 -0.315486865  0.299107816
## [147,]  1.605216358  1.3609647044  0.058279888  1.297625876
## [148,]  2.682788860  0.6875274116  0.114497282  1.550471362
## [149,] -0.353167691  1.2850815149  0.526294287  0.539039927
## [150,] -0.176403759  1.1026904032  0.272056552  0.668832279
## [151,]  2.061713247 -2.1827470849 -0.416352060  0.620910619
## [152,]  0.381162710  0.1546923885  0.365823708 -1.200276616
## [153,] -0.372488230 -0.2812185971  0.967255986 -0.789700429
## [154,] -1.427336043 -0.6807734154  1.881507390 -0.086634374
## [155,]  1.161072403  0.5332381038  2.075108311 -0.570143122
## [156,]  0.974899148 -0.0136699350  2.393923008  0.165772096
## [157,]  3.581349710 -1.2262484268 -0.513021506  0.605439432
## [158,]  1.341667562 -0.0337896071 -0.177686014 -0.742290703
## [159,]  1.482548304  0.2428043266 -0.382469964 -1.493601815
## [160,] -0.569215287 -0.0007267122  0.681836951 -1.076895721
## [161,]  0.782394132  0.9418545137  0.677221033 -1.865093337
## [162,] -0.248941648 -0.1965054935  1.709658033 -0.238575098
## [163,] -0.062523170 -0.4851524116  1.102199982 -0.448454860
## [164,]  0.700581281 -0.0827572589  0.481831818 -0.869705087
## [165,] -0.941008732 -0.4781085544  1.079026788 -0.457084945
## [166,]  0.141067015 -0.5739869117  0.679282573 -0.512877991
## [167,]  2.468565271  0.9144947006 -0.639007220  0.880717293
## [168,]  2.881480694  1.0855845810 -1.014211985  0.092275687
## [169,]  2.906074845 -0.4184865989 -0.162771943 -0.466333610
## [170,]  0.800153914  2.0583521919  0.912902583  0.133417883
## [171,] -0.119562306  1.2420666333 -1.565197556 -0.634373289
## [172,]  1.178556139  1.2852409530  1.634832733  1.290274288
## [173,] -0.306972030  1.2995394319  0.534929834  0.400800169
## [174,] -0.437746589  2.2489781502 -0.314860367 -0.797070792
## [175,]  3.289592138  0.2903328597 -0.468414474  1.378022614
## [176,]  0.800153914  2.0583521919  0.912902583  0.133417883
## [177,]  0.788975903 -0.0682462257  0.987144838 -1.021696938
## [178,] -0.301305515  0.2977026172  1.687498558 -0.786323875
## [179,]  5.524473008 -0.8644020693 -0.760282662 -0.704872411
## [180,]  0.280008410 -0.4184365408  1.585801228 -0.351871016
## [181,]  2.715469276 -0.9255347766  0.512692181  0.239517010
## [182,]  1.816222507  1.7206194430 -0.261421539 -0.930937412
## [183,]  2.992713941  1.0219240709 -0.604378146  1.303692980
## [184,]  0.044327116 -0.2988580582  0.778517461 -1.023496462
## [185,]  2.033258424  0.4276891968  2.221523639 -0.587885894
## [186,]  3.912577118 -0.2500886930  0.376241636 -0.512672500
## [187,]  3.079006603  0.6716386127 -0.293057492 -2.060211306
## [188,]  1.606957897  1.4191964406  1.234187459 -2.141796301
## [189,]  3.200710931  1.9866031666  0.861814599 -0.442726188
## [190,]  5.816373029  2.0848029360  0.837675186 -0.379748901
## [191,] -1.211712875  0.3668094378 -1.200152597  0.706798438
## [192,] -1.543280368  0.2269989895 -0.334886545  1.272656216
## [193,] -0.497850504 -1.0858324566 -1.840057570 -0.922896976
## [194,] -0.609752454  1.4723131920 -0.961487487  0.109175075
## [195,] -1.426261986  1.5481964915  0.632285111  0.804983950
## [196,] -0.864941946  1.1713593868 -0.943530349  0.290367857
## [197,] -1.964564589 -0.4849555015 -0.653831891  1.582711763
## [198,] -0.727609175  0.3725670980 -1.126242975  0.871231589
## [199,] -0.831137111  1.4248120900 -0.285152793  0.549543630
## [200,] -1.158180772  0.9408875745 -1.697647460  0.011277480
## [201,] -1.128142095  0.8357625480 -0.414233478  0.640140470
## [202,] -1.857602850 -0.2690955028 -0.761335334  1.372786794
## [203,]  0.499344345  1.0387081960 -2.001586359 -0.108642214
## [204,] -0.501164102  0.1321308790 -1.643818580  0.880545382
## [205,]  1.074330951  0.7761607818 -1.480761193 -0.172742495
## [206,] -1.149017829  0.8705260213 -1.031840079  0.226270994
## [207,] -0.957121625  0.6842849239 -0.761484024  0.731021818
## [208,] -0.767073236  0.9042396188 -1.231954333  0.152875549
## [209,] -0.141052304  0.4452822793 -1.429226013  0.718929470
## [210,] -2.210265153  0.6342983022 -1.230774501  0.215057393
## [211,] -0.488802857  0.8219097157 -3.090972563 -0.659275890
## [212,] -1.709477421 -0.6485597798 -1.846866648  0.813616147
## [213,] -0.447203891  0.9873228956 -2.289246297 -0.274541158
## [214,] -0.695955591  1.2977381508 -2.375618016 -0.779602604
## [215,] -1.328870233  0.9780283542 -0.193662967  0.796060338
## [216,] -0.087245230  0.7966780786 -2.081007252 -0.018419477
## [217,] -1.747635381  1.3357469468 -0.737319239 -0.065300179
## [218,]  0.435849647  0.0706985095 -0.806694054 -1.211049107
## [219,] -1.002675385 -1.4095067449  0.606369030  0.562735582
## [220,]  0.439911469 -0.3331600428 -2.301543747 -1.873334592
## [221,] -0.551688989 -1.2106098256 -1.374356648 -0.874311003
## [222,] -1.204011995 -0.3826813700 -0.132852565 -0.912986154
## [223,] -0.932091391 -1.1241713941 -0.321132927 -0.292349066
## [224,] -2.631724980 -3.4922633666 -2.402907331 -0.117672526
## [225,] -1.499168776 -0.6166033332  0.443462490 -0.475562900
## [226,] -1.285954025 -1.4773782728 -0.061127940 -0.030760283
## [227,]  0.083566574 -1.0454628683 -0.861056085 -0.359362313
## [228,]  0.660710043 -1.5235041670 -1.106504934 -0.057545604
## [229,] -0.198713007 -1.8599984450 -1.236016067 -0.170691381
## [230,] -0.060241790 -1.7001171675 -0.165448152  0.267697057
## [231,] -0.645019313 -0.5212420971  0.960271674  0.133750241
## [232,] -0.469296798 -1.5196906328 -0.027805351  0.308382464
## [233,]  7.499324999 -2.3277511944 -1.349276550  2.383007665
## [234,] -0.239836188 -0.2924191990  0.297303041 -0.663135566
## [235,] -0.872516238 -1.5833839256 -0.520899041 -0.582201505
## [236,] -0.598002047 -0.6751856547  0.871097979  0.056613132
## [237,] -0.376014364  0.4470632562  1.498427150 -0.412129830
## [238,] -0.662718647 -0.5972441504  0.446878102 -0.252310774
## [239,] -1.444172973 -0.4947160725  0.871721255 -0.250143384
## [240,] -1.244840762 -1.3506173111  0.094137662 -0.110436210
## [241,] -1.843997103 -1.1581382491 -0.004450434 -0.390553445
## [242,] -1.616485611 -1.2496429692  0.199935828 -0.152089207
## [243,] -0.768872045 -1.6248411490  0.009311189  0.355764527
## [244,] -0.955320139 -1.0419841435 -0.679055615  2.010637986
## [245,] -0.502207556  0.6048649308 -0.514160755  1.092338962
## [246,] -1.044586387  1.0727052876 -0.752898084  0.322548322
## [247,] -1.245945961  0.8855033931  0.122826826  0.975099007
## [248,] -1.262296822  0.7596973015 -0.089785968  1.187348334
## [249,] -0.756160108  0.9165304349 -0.118365232  1.020760933
## [250,]  0.665712318 -1.2016436180  0.112513900  0.115778659
## [251,] -0.608977132 -0.6442351279 -1.004735535 -1.260257715
## [252,]  0.121503591 -1.5698282927 -0.936140449 -0.799271692
## [253,] -0.538370298 -0.2787301349  0.893636618 -0.143221548
## [254,]  0.562020467 -0.9371781534  0.512114818  0.329291428
## [255,]  0.230597869 -0.0827071968 -1.912184320  0.781825026
## [256,] -0.783364519  0.4399454963 -0.904500964  0.814996037
## [257,] -1.610353150  0.0439859524  0.140518032  1.495651114
## [258,] -0.810984764  0.1957231360 -0.833615495  0.940179073
## [259,] -1.104262654  0.4152546080 -0.259901481  1.184472673
## [260,] -0.224060930  0.4057124979 -0.274442099  1.127189091
## [261,]  0.960508359  0.0139881349 -1.176167846  1.599005403
## [262,] -0.802191000  1.5523004872 -0.598872695 -0.130109072
## [263,] -0.114059468  1.3742593751  0.771255450  1.194814620
## [264,] -1.124983911 -0.8009659584  1.369778947  0.194242790
## [265,]  0.026278597 -0.9969242698 -0.389556292 -0.552163042
## [266,]  0.193399531  0.0848160242 -0.261748330 -1.070827573
## [267,] -1.398109287 -0.2672358745 -0.370535704 -1.275303624
## [268,] -0.087208289 -0.0959725531 -1.402468409 -1.759912412
## [269,] -0.126746970 -1.3519305882  0.039343055  0.194688179
## [270,] -0.638651336 -0.4450159288  0.980717611 -0.172603781
## [271,] -1.678087327 -0.7420303730  0.710510599 -0.443001994
## [272,]  0.122951879  1.0251511097  0.030183713  1.110654018
## [273,] -1.022245694  1.1341237104 -0.144128176  0.323741841
## [274,] -1.046084973  0.7078725655  0.265883821  1.003906950
## [275,] -0.798929039 -0.3525961486  0.737318323 -0.526334987
## [276,] -0.179645549 -1.3106483352  0.733628384  0.464188356
## [277,] -0.115016996 -1.5094555514 -0.650777849 -0.655356293
## [278,]  2.433778420 -2.3787526594 -0.881421563  1.372787090
## [279,] -0.417530809  0.7650402692  0.453934247  1.031910861
## [280,]  0.523770069 -0.0323346249  1.967023349 -0.010026759
## [281,] -0.583983055 -0.9822176469  0.217086839 -0.290718131
## [282,] -0.539902096 -0.9125118741  0.994234758  0.278782180
## [283,] -1.163861330 -1.2158522713 -0.366498922 -0.604696533
## [284,] -1.151646791 -1.0221470253 -0.236009127 -0.818683014
## [285,]  0.063663556  0.2214526709  1.045847056 -0.708195359
## [286,]  3.770288669 -0.3535923578 -1.949494485 -0.806155049
## [287,] -1.214269493 -0.2076327522  1.915674458 -0.208257620
## [288,] -0.292308350 -0.4394159588  1.487151395  0.063677202
## [289,]  0.579365180 -1.4193773055 -0.751322965 -0.186390071
## [290,] -0.557038557 -0.2933544902  0.951566088 -0.711968313
## [291,] -0.359927243 -0.6145438461  0.870407948 -0.168788689
## [292,] -1.474633105 -0.8905157483  1.169458775 -0.005986308
## [293,] -0.773114985 -0.1686458508  0.735500118 -0.833798880
## [294,]  1.136103940 -1.6537170629  0.346416938 -0.089869503
## [295,]  2.214795141 -0.8377969977 -0.728586588 -0.379577670
## [296,]  0.045777948 -1.2862766078  1.036560208  0.026540706
## [297,] -0.697732783 -1.2816072724  0.530991791 -0.087832386
## [298,]  0.460648862 -0.7244624028  0.078261156 -0.562934330
## [299,] -0.484047463  0.0833721991  1.426043029 -0.384886905
## [300,]  7.428486746 -3.0418468425 -0.485672383  3.497475982
## [301,]  0.520438852 -0.0616233237  1.466424033  0.041547622
## [302,] -1.209570684 -0.3400545171  1.401442018 -0.469345541
## [303,] -0.825016983 -0.0824314463  1.992993517 -0.054366319
## [304,]  0.019541046  0.2407566436  2.686915856 -0.140520873
## [305,]  0.963822468  0.3803679608 -0.582625540 -1.396307777
## [306,]  0.286636239  0.0637426851  0.862830849 -0.755017470
## [307,]  1.874169445 -0.6033882472  0.440107664 -0.764712469
## [308,]  0.192587515  0.2906143053 -0.067267674  1.353290128
## [309,] -0.998783230  1.6286066537  0.529438825  0.161379250
## [310,]  0.909176511  2.4463112476 -0.389632447 -0.583293090
## [311,]  1.816707338  0.4528648542  0.410827632  1.437921746
## [312,]  2.641072388  1.5986111873 -0.587141159  0.002109684
## [313,] -0.628610787  1.1832460073  1.567594526  0.807641464
## [314,] -0.421970775  1.5827157302  0.443581127  0.350945719
## [315,] -0.195458409  1.1144375239  1.641616379  1.750264782
## [316,]  4.547874402  1.2278049494 -0.121268385  0.241895265
## [317,]  5.181647815  0.3405859616 -0.342518423  2.316053031
## [318,] -0.307688399  1.6163536563 -0.052673936 -0.246474473
## [319,]  0.680088214  0.4112726565  1.088382847 -0.952594567
## [320,]  0.775583156  0.6298719078  0.334126466 -1.706025905
## [321,] -0.258828443  0.1328362540 -1.125202085 -2.322011781
## [322,]  0.238627770 -0.5183891386  1.639892991  0.008688611
## [323,]  6.219328664 -0.3746903126  0.869875846 -0.928851659
## [324,] -1.182660542 -0.7585108022  1.109091084 -0.486484332
## [325,] -0.008972528  1.2164848919  0.658802315  0.848643946
## [326,]  1.698677031  0.5581885912  0.212767965  2.013389161
## [327,]  1.187926435  1.3488186457  0.172204685  0.704532511
## [328,] -0.232421156  0.7698620312  0.325995787  0.914722988
## [329,]  1.094870462  3.1147291003 -0.901824443 -1.582454606
## [330,] -0.416248578 -1.1388695688  0.593479193 -0.610325116
## [331,]  2.920425102  0.0163639109  1.496501964 -1.713783661
## [332,]  0.591593977  0.9943006409  1.404254381 -1.628831658
## [333,]  0.899551894  1.2980838091  1.448968600 -1.458685989
## [334,]  2.984832646 -0.5403654799 -0.484486898 -1.211777969
## [335,]  1.505305395  2.7057682574 -2.135790063 -1.943632643
## [336,]  0.490808021  1.1681019995  1.563956940  1.229961627
## [337,]  0.467032336  0.7140818457 -1.284020555 -2.986989373
## [338,]  1.564729628  0.3731876458  0.061063590 -1.594893795
## [339,] -0.151307375  0.3034511489  0.209318320 -1.865223557
## [340,]  2.180233903 -1.1044635612  0.648227065  0.116418033
## [341,]  1.252382803  2.7755478581  1.428928180 -0.346608453
## [342,]  4.901142691 -0.1198332117  1.523238305 -0.915810258
## [343,]  3.461396538  2.4043144117  1.123568816 -0.025538799
## [344,]  0.932619239  2.2182227163  1.178903139 -0.269505375
## [345,]  4.438259643  3.1481593802  0.688666238 -0.943946430
#Uso del algoritmo kmeans
clustering<-kmeans(componentes_prin, 3)
clustering
## K-means clustering with 3 clusters of sizes 42, 173, 130
## 
## Cluster means:
##          PC1        PC2         PC3        PC4
## 1  3.4333410 -0.2032703 -0.03254866  0.2064720
## 2 -0.3984542 -0.6259153  0.32597513 -0.5117194
## 3 -0.5789827  0.8986207 -0.42328195  0.6142741
## 
## Clustering vector:
##   [1] 3 2 2 2 2 2 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3
##  [36] 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 2 2 2 2 2 2 2 2 2 2 2 3 3 2 2 2 2
##  [71] 3 3 3 3 3 3 1 2 2 2 2 2 2 2 1 2 2 2 3 3 3 3 3 3 3 3 2 2 2 2 2 2 3 3 3
## [106] 3 3 3 3 2 2 2 2 2 1 2 2 2 2 2 1 2 2 2 2 2 2 2 2 2 3 3 1 1 2 2 2 2 2 2
## [141] 3 3 3 3 3 3 3 1 3 3 1 2 2 2 2 2 1 2 2 2 2 2 2 2 2 2 1 1 1 3 3 3 3 3 1
## [176] 3 2 2 1 2 1 1 1 2 1 1 1 2 1 1 3 3 2 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3
## [211] 3 3 3 3 3 3 3 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 2 2 2 2 2 2 2 2 2 2 3 3
## [246] 3 3 3 3 2 2 2 2 2 3 3 3 3 3 3 3 3 3 2 2 2 2 2 2 2 2 3 3 3 2 2 2 1 3 2
## [281] 2 2 2 2 2 1 2 2 2 2 2 2 2 2 1 2 2 2 2 1 2 2 2 2 2 2 1 3 3 3 1 1 3 3 3
## [316] 1 1 3 2 2 2 2 1 2 3 1 3 3 3 2 1 2 2 1 3 3 2 2 2 1 3 1 1 3 1
## 
## Within cluster sum of squares by cluster:
## [1] 288.7016 439.1094 322.6786
##  (between_SS / total_SS =  45.5 %)
## 
## Available components:
## 
## [1] "cluster"      "centers"      "totss"        "withinss"    
## [5] "tot.withinss" "betweenss"    "size"         "iter"        
## [9] "ifault"
#Convertimos a dataframe la matriz componentes_prin
componentes_prin<-as.data.frame(componentes_prin)

plot(componentes_prin$PC1,componentes_prin$PC2, col=clustering$cluster)

plot(componentes_prin$PC2,componentes_prin$PC3, col=clustering$cluster)

plot(componentes_prin$PC3,componentes_prin$PC4, col=clustering$cluster)

plot(componentes_prin$PC1,componentes_prin$PC4, col=clustering$cluster)

plot(componentes_prin$PC2,componentes_prin$PC4, col=clustering$cluster)

#Usamos la libreria rgl para ahcer graficos 3d
library(rgl)
plot3d(x=componentes_prin$PC1,y=componentes_prin$PC2,z=componentes_prin$PC3, col=clustering$cluster)
##APLICAMOS EL ALGORITMO PAM
bupa_scale<- scale(bupa)
library(cluster)
library(factoextra)
## Loading required package: ggplot2
## 
## Attaching package: 'ggplot2'
## The following objects are masked from 'package:psych':
## 
##     %+%, alpha
## Welcome! Related Books: `Practical Guide To Cluster Analysis in R` at https://goo.gl/13EFCZ

Lo primero que debemos de hacer es escalar la data para que las variables esten en las mismas unidades. Tambien se instalarán los paquetes “cluster” (Nos ayuda a encontrar grupos en la data) y “factoextra” (Sirve para la extraccion y visualizacion de los resultados del analisis de datos multivariados)

#Identificar el número óptimo de clusters
fviz_nbclust(x = bupa_scale,FUNcluster = pam, method="wss" , k.max = 7,
             diss = dist(bupa_scale,method = "euclidean"))

Aplicamos el metodo del codo para encontrar la cantidad optima de clusters, asignamos una cantidad maxima de clusters de 7. En este caso el metodo a utilizar fue “euclidean” ya que la data no contaba con outliers

#Específica la cantidad de grupos
set.seed(111)
pam_cluster <- pam(x = bupa_scale,k = 3,metric = "euclidean")
pam_cluster
## Medoids:
##       ID          V1         V2         V3         V4          V5
## [1,]  74 -0.03584012  0.1706176  0.1842018 -0.3620131 -0.41483167
## [2,]  99 -0.26065541 -0.2654051 -0.2257958 -0.6600907 -0.05818572
## [3,] 169  0.63860576  0.7701487  1.4141947  2.2213260  0.60415677
##              V6         V7
## [1,] -0.4359330 -1.1727371
## [2,] -0.1363376  0.8502344
## [3,]  1.0620439  0.8502344
## Clustering vector:
##   [1] 1 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
##  [36] 3 2 2 2 2 3 2 2 2 2 2 2 2 2 2 2 2 3 2 2 2 2 2 2 2 2 2 2 2 1 1 2 2 2 2
##  [71] 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 2 2 2 2 2 2 1 1 1
## [106] 1 1 1 1 2 3 2 2 2 3 2 2 2 2 2 3 2 2 2 2 2 2 2 2 2 1 1 3 3 2 2 2 2 2 2
## [141] 1 1 1 1 1 1 1 3 1 1 3 2 2 2 2 2 3 3 3 2 2 2 2 2 2 2 3 3 3 1 1 1 1 1 3
## [176] 1 2 2 3 2 3 1 3 2 3 3 3 3 3 3 1 1 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
## [211] 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 3 2 2 2 2 2 2 2 2 2 2 1 1
## [246] 1 1 1 1 2 2 2 2 2 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 1 1 1 2 2 2 3 1 2
## [281] 2 2 2 2 2 3 2 2 2 2 2 2 2 2 3 2 2 2 2 3 2 2 2 2 2 2 3 1 1 1 1 3 1 1 1
## [316] 3 3 1 2 2 2 2 3 2 1 1 1 1 1 2 3 2 2 3 1 1 2 3 2 3 1 3 3 1 3
## Objective function:
##    build     swap 
## 1.958425 1.958425 
## 
## Available components:
##  [1] "medoids"    "id.med"     "clustering" "objective"  "isolation" 
##  [6] "clusinfo"   "silinfo"    "diss"       "call"       "data"

Para que nos salga los mismos resultados ponemos una semilla de ‘111’, luego especificamos la cantidad de clusters con ‘pam’ y se asigna el tipo de metrica a “euclidean”.(En este caso la cantidad óptima de cluster es 3)

#Diagrama de dispersión
fviz_cluster(object = pam_cluster, data = bupa_scale,geom = "point",
             ellipse.type = "t",repel = TRUE)+
  theme_bw() +
  labs(title = "ALGORITMO PAM")

En esta parte se diseña un diagrama de dispersión para la visualizacion del algoritmo de PAM, en donde nos muestra 3 clusters

##APLICAMOS EL ALGORITMO CLARA
# Diagrama de dispersión 
clara_cluster<-clara(bupa,3)
fviz_cluster(clara_cluster,stand = TRUE,geom = "point",pointsize = 1)+
  theme_bw() +
  labs(title = "ALGORITMO CLARA")

Para el uso de CLARA, se crea una variable llamada “clara_cluster” con la cual se trabajará en el siguiente codigo, el cual nos diseñara un gráfico que formara los clusters que se le asignó